A Workload-Dependent Performance Analysis of an In-Memory Database in a Multi-Tenant Configuration

Abstract

Modern in-memory database systems begin to provide multi-tenancy features. In contrast to the traditional operation of one large database appliance per system, the utilization of the multi-tenancy features allows for multiple database containers running on one system. Consequently, the database tenants share the same system resources, which has an influence on their performance. Understanding the performance of database tenants in different setups with varying workloads is a challenging task. However, knowledge of the performance behavior is crucial in order to benefit from multi-tenancy. In this paper, we provide fine-grained performance insights of the in-memory database SAP HANA in a multi-tenant configuration. We perform multiple benchmark runs utilizing an online analytical processing benchmark in order to retrieve information about the performance behavior of the multi-tenant database containers. Furthermore, we provide an analysis of the collected results and show a more efficient usage of threads in an environment with less active tenants under specific workload conditions.